Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (arr
    -0.07
    (todo
    -0.07
    ío
    -0.06
    код
    -0.06
    ascii
    -0.06
    駅
    -0.06
    LayoutManager
    -0.06
    Mutex
    -0.06
    ('/')[-
    -0.06
     필요한
    -0.06
    POSITIVE LOGITS
     destroys
    0.07
    操作
    0.07
     striking
    0.07
     Techniques
    0.06
     cope
    0.06
     �
    0.06
     Wimbledon
    0.06
     Rec
    0.06
     stř
    0.06
     interpretations
    0.06
    Act Density 0.034%

    No Known Activations